multica

Project Overview

Multica is an open-source workspace where you assign work to AI coding agents the way you'd assign it to a teammate — they pick up the issue, report progress, raise blockers, and hand it back for review. Self-hostable, works with 26 agent CLIs, no lock-in.

Key Features

• 26 agent CLIs: Claude Code, Codex, Cursor, Copilot, Kimi, OpenCode, and more
• Agents as teammates: Give each one a name, a provider, and a runtime — they show up on the board
• Squads: Put agents and people on one team; the leader routes the work
• Skills: Turn a solved problem into a playbook every agent reuses
• Execution log: Replay every tool call, command, and decision
• Autopilots: Run standups, audits, and reports on a schedule

Target Audience

• Developers using multiple AI coding agents
• Organizations that want to integrate AI agents into team workflows
• Teams who need a self-hostable agent collaboration platform

Quick Start

1. Visit the Multica quickstart
2. Download Multica and install
3. Configure agents and runtimes, then start assigning tasks

Core Advantages

• Self-hostable with full data control
• Supports 26 mainstream AI agents
• Agents work like teammates with no extra management overhead
• Open-source and lock-in free